Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 46006
    Prev
    Next
    INDEX
    Explanations

    topics related to risk assessment and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    480
    +0.52
    2.7%
    266
    +0.13
    0.7%
    665
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.52
    0.01
    266
    +0.13
    0.06
    665
    +0.10
    0.04
    Negative Logits
    eware
    -0.58
    aina
    -0.57
    allion
    -0.55
    interstitial
    -0.55
    anamo
    -0.54
    umbnails
    -0.53
    allery
    -0.52
    joice
    -0.52
    ikini
    -0.51
    ĸļ
    -0.51
    POSITIVE LOGITS
     foreseeable
    0.74
     ourselves
    0.72
    externalActionCode
    0.67
     timelines
    0.64
     unless
    0.64
     sooner
    0.61
    plementation
    0.60
     feasible
    0.60
     someday
    0.59
    mediate
    0.59
    Activations Density 0.445%

    No Known Activations